Test assistent MCP server

Overview Schema Source Related Servers Discussions Admin

generate_test_cases

Generate concrete test cases from one classic technique: boundaries, equivalence classes, decision tables, pairwise, state transitions, use cases or error guessing.

Instructions

Generate concrete test cases using a classic test technique (Boundary Value Analysis, Equivalence Partitioning, Decision Table, Pairwise Testing, State Transition, Use Case Testing, Error Guessing). Each call targets exactly one technique. For raw typed test data (random rows or property-based), use generate_test_data instead.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`input`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.1.0Sep 11, 2026

addedInput schema / $defs

Added value: +{
+  "BoundaryValueSpec": {
+    "properties": {
+      "field": {
+        "description": "Field name",
+        "title": "Field",
+        "type": "string"
+      },
+      "max": {
+        "description": "Inclusive upper boundary",
+        "title": "Max",
+        "type": "integer"
+      },
+      "min": {
+        "description": "Inclusive lower boundary",
+        "title": "Min",
+        "type": "integer"
+      },
+      "technique": {
+        "const": "Boundary Value Analysis",
+        "description": "Generate test cases around and beyond the min/max range edges",
+        "title": "Technique",
+        "type": "string"
+      }
+    },
+    "required": [
+      "technique",
+      "field",
+      "min",
+      "max"
+    ],
+    "title": "BoundaryValueSpec",
+    "type": "object"
+  },
+  "DecisionTableSpec": {
+    "properties": {
+      "actions": {
+        "description": "Action names",
+        "items": {
+          "type": "string"
+        },
+        "title": "Actions",
+        "type": "array"
+      },
+      "conditions": {
+        "description": "Condition names",
+        "items": {
+          "type": "string"
+        },
+        "title": "Conditions",
+        "type": "array"
+      },
+      "rules": {
+        "description": "Rules, each {'when': {cond: value}, 'then': [action, ...]}",
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "title": "Rules",
+        "type": "array"
+      },
+      "technique": {
+        "const": "Decision Table",
+        "description": "Decision table with condition-action rules; one test case per rule",
+        "title": "Technique",
+        "type": "string"
+      }
+    },
+    "required": [
+      "technique",
+      "conditions",
+      "actions"
+    ],
+    "title": "DecisionTableSpec",
+    "type": "object"
+  },
+  "EquivalenceSpec": {
+    "properties": {
+      "field": {
+        "description": "Field name",
+        "title": "Field",
+        "type": "string"
+      },
+      "invalid": {
+        "description": "Values expected to be rejected",
+        "items": {},
+        "title": "Invalid",
+        "type": "array"
+      },
+      "technique": {
+        "const": "Equivalence Partitioning",
+        "description": "One test case per explicit valid and invalid value",
+        "title": "Technique",
+        "type": "string"
+      },
+      "valid": {
+        "description": "Values expected to be accepted",
+        "items": {},
+        "title": "Valid",
+        "type": "array"
+      }
+    },
+    "required": [
+      "technique",
+      "field",
+      "valid",
+      "invalid"
+    ],
+    "title": "EquivalenceSpec",
+    "type": "object"
+  },
+  "ErrorGuessingSpec": {
+    "properties": {
+      "field": {
+        "description": "Field name",
+        "title": "Field",
+        "type": "string"
+      },
+      "input": {
+        "description": "A representative valid value",
+        "title": "Input"
+      },
+      "pitfalls": {
+        "description": "Known error-prone values to try",
+        "items": {},
+        "title": "Pitfalls",
+        "type": "array"
+      },
+      "technique": {
+        "const": "Error Guessing",
+        "description": "Negative test cases from known error-prone pitfalls",
+        "title": "Technique",
+        "type": "string"
+      }
+    },
+    "required": [
+      "technique",
+      "field",
+      "input",
+      "pitfalls"
+    ],
+    "title": "ErrorGuessingSpec",
+    "type": "object"
+  },
+  "PairwiseSpec": {
+    "properties": {
+      "technique": {
+        "const": "Pairwise Testing",
+        "description": "All-pairs covering set of parameter combinations",
+        "title": "Technique",
+        "type": "string"
+      },
+      "values": {
+        "additionalProperties": {
+          "items": {},
+          "type": "array"
+        },
+        "description": "Map of parameter name to list of values to combine",
+        "title": "Values",
+        "type": "object"
+      }
+    },
+    "required": [
+      "technique",
+      "values"
+    ],
+    "title": "PairwiseSpec",
+    "type": "object"
+  },
+  "StateTransitionSpec": {
+    "properties": {
+      "events": {
+        "description": "Possible events",
+        "items": {
+          "type": "string"
+        },
+        "title": "Events",
+        "type": "array"
+      },
+      "states": {
+        "description": "Possible states",
+        "items": {
+          "type": "string"
+        },
+        "title": "States",
+        "type": "array"
+      },
+      "technique": {
+        "const": "State Transition",
+        "description": "State-event transitions; one test case per transition",
+        "title": "Technique",
+        "type": "string"
+      },
+      "transitions": {
+        "description": "Transitions, each {'state': s, 'event': e, 'next': n}",
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "title": "Transitions",
+        "type": "array"
+      }
+    },
+    "required": [
+      "technique",
+      "states",
+      "events"
+    ],
+    "title": "StateTransitionSpec",
+    "type": "object"
+  },
+  "UseCaseSpec": {
+    "properties": {
+      "expected": {
+        "description": "Expected outcomes per step (parallel to steps)",
+        "items": {
+          "type": "string"
+        },
+        "title": "Expected",
+        "type": "array"
+      },
+      "name": {
+        "description": "Use case name",
+        "title": "Name",
+        "type": "string"
+      },
+      "steps": {
+        "description": "Ordered steps of the use case",
+        "items": {
+          "type": "string"
+        },
+        "title": "Steps",
+        "type": "array"
+      },
+      "technique": {
+        "const": "Use Case Testing",
+        "description": "End-to-end use case steps; one test case per step",
+        "title": "Technique",
+        "type": "string"
+      }
+    },
+    "required": [
+      "technique",
+      "name",
+      "steps"
+    ],
+    "title": "UseCaseSpec",
+    "type": "object"
+  }
+}

addedInput schema / properties / input

Added value: +{
+  "discriminator": {
+    "mapping": {
+      "Boundary Value Analysis": "#/$defs/BoundaryValueSpec",
+      "Decision Table": "#/$defs/DecisionTableSpec",
+      "Equivalence Partitioning": "#/$defs/EquivalenceSpec",
+      "Error Guessing": "#/$defs/ErrorGuessingSpec",
+      "Pairwise Testing": "#/$defs/PairwiseSpec",
+      "State Transition": "#/$defs/StateTransitionSpec",
+      "Use Case Testing": "#/$defs/UseCaseSpec"
+    },
+    "propertyName": "technique"
+  },
+  "oneOf": [
+    {
+      "$ref": "#/$defs/BoundaryValueSpec"
+    },
+    {
+      "$ref": "#/$defs/EquivalenceSpec"
+    },
+    {
+      "$ref": "#/$defs/DecisionTableSpec"
+    },
+    {
+      "$ref": "#/$defs/PairwiseSpec"
+    },
+    {
+      "$ref": "#/$defs/StateTransitionSpec"
+    },
+    {
+      "$ref": "#/$defs/UseCaseSpec"
+    },
+    {
+      "$ref": "#/$defs/ErrorGuessingSpec"
+    }
+  ],
+  "title": "Input"
+}

removedInput schema / properties / inputs

Removed value: -{
-  "additionalProperties": true,
-  "title": "Inputs",
-  "type": "object"
-}

removedInput schema / properties / technique

Removed value: -{
-  "title": "Technique",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "technique",
-  "inputs"
-]New value: +[
+  "input"
+]

First observedv0.1.0Sep 9, 2026

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the meaningful behavioral constraint that exactly one technique is processed per call, but says nothing about determinism, validation failures, error behavior on malformed specs, or side effects. The presence of an output schema removes the need to describe return values, which keeps this at a moderate score rather than low.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and the technique enumeration, with the sibling routing last. The parenthetical technique list is dense but earns its place because those strings are the discriminator values; no wasted prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a polymorphic one-parameter tool with a rich output schema, the description covers purpose, the one-technique-per-call rule, and the main sibling alternative, so return values need not be explained. It stops short of explaining how the union input is selected per technique or what happens on an unrecognized/invalid spec, leaving gaps for a tool whose input is a discriminated union.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Top-level schema description coverage is reported at 0%, so the description must compensate, and it partially does by naming all seven technique values that the discriminator accepts. However, it gives no guidance on the per-technique payload shape (which fields each variant requires), so an agent must still read the $defs to build a valid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Generate concrete test cases") and enumerates the seven supported techniques, which maps directly onto the schema's discriminator constants. It also names the sibling it is not (generate_test_data), so an agent can separate these two tools without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes one case: "For raw typed test data (random rows or property-based), use generate_test_data instead." It also states the constraint that each call targets exactly one technique. Missing only guidance against the other siblings, notably advise_technique, which an agent could easily confuse with this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server